Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Start of sentences/Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     @_
    -0.07
    _SM
    -0.07
    .we
    -0.07
    𝘪
    -0.07
    @Path
    -0.06
    /network
    -0.06
    	fi
    -0.06
    .tw
    -0.06
    .Ch
    -0.06
     países
    -0.06
    POSITIVE LOGITS
    סאות
    0.08
    ünün
    0.07
    uted
    0.07
    uil
    0.07
    ときは
    0.07
    .Quantity
    0.07
     Buccaneers
    0.07
    樽
    0.07
    届毕业生
    0.07
    누
    0.07
    Act Density 0.069%

    No Known Activations